INDEX
Explanations
the word "shoes"
references to shoes
New Auto-Interp
Negative Logits
erest
-0.73
itative
-0.72
subp
-0.69
PsyNetMessage
-0.68
arios
-0.66
VD
-0.65
itement
-0.64
Democr
-0.63
76561
-0.63
REDACTED
-0.62
POSITIVE LOGITS
horn
1.10
shoes
1.10
Shoes
0.99
bridge
0.97
pee
0.94
prints
0.89
toe
0.87
mens
0.86
socks
0.85
ets
0.84
Activations Density 0.013%